Title :
A new design strategy for the Tank and Hopfield neural analog-to-digital converter
Author :
Dempsey, G.L. ; Pintoy, A.G. ; Wood, J.A.
Author_Institution :
Dept. of Electr. & Comput. Eng. Technol., Bradley Univ., Peoria, IL, USA
Abstract :
Tank and Hopfield (1986) have described the implementation of a neural-based 4-bit analog-to-digital converter and discussed several of the problems they encountered such as missing output codes. High-gain amplifiers were used for the artificial neurons in their implementation. System noise and non-ideal amplifier characteristics such as offset voltages are multiplied by gain which results in a loss of conversion accuracy. The new approach proposed here use low-gain analog amplifiers for the artificial neurons where the gain is more like that of a biological neutron. Simulation and experimental results are presented
Keywords :
Hopfield neural nets; amplifiers; analogue-digital conversion; 4 bit; 4-bit analog-to-digital converter; Tank and Hopfield neural ADC; artificial neurons; biological neutron; conversion accuracy; experimental results; low-gain analog amplifiers; non-ideal amplifier characteristics; offset voltages; simulation results; system noise; Analog-digital conversion; Artificial neural networks; Biological information theory; Biological system modeling; Costs; Differential equations; Image resolution; Low-noise amplifiers; Neurons; Neutrons; Temperature; Voltage;
Conference_Titel :
Signals, Systems and Computers, 1993. 1993 Conference Record of The Twenty-Seventh Asilomar Conference on
Conference_Location :
Pacific Grove, CA
Print_ISBN :
0-8186-4120-7
DOI :
10.1109/ACSSC.1993.342538
